INDEX

Explanations

references to players and teams in sports contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 èµ¤

-0.15

yat

-0.15

lossen

-0.15

ÙģØ§ÙĦ

-0.14

 Fulton

-0.14

velt

-0.14

çĸĨ

-0.14

.cm

-0.14

ROSS

-0.14

ãģĹãĤĩ

-0.14

POSITIVE LOGITS

 Leicester

0.37

fox

0.23

Fox

0.22

Fox

0.22

Hin

0.22

fox

0.20

icester

0.20

LC

0.19

FOX

0.18

utex

0.17

Activations Density 0.010%

references to players and teams in sports contexts

No Comments

No Known Activations